FedBEns: One-Shot Federated Learning based on Bayesian Ensemble

Jacopo Talpini, Marco Savi, Giovanni Neglia
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:58448-58466, 2025.

Abstract

One-Shot Federated Learning (FL) is a recent paradigm that enables multiple clients to cooperatively learn a global model in a single round of communication with a central server. In this paper, we analyze the One-Shot FL problem through the lens of Bayesian inference and propose FedBEns, an algorithm that leverages the inherent multimodality of local loss functions to find better global models.Our algorithm leverages a mixture of Laplace approximations for the clients’ local posteriors, which the server then aggregates to infer the global model. We conduct extensive experiments on various datasets, demonstrating that the proposed method outperforms competing baselines that typically rely on unimodal approximations of the local losses.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-talpini25a, title = {{F}ed{BE}ns: One-Shot Federated Learning based on {B}ayesian Ensemble}, author = {Talpini, Jacopo and Savi, Marco and Neglia, Giovanni}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {58448--58466}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/talpini25a/talpini25a.pdf}, url = {https://proceedings.mlr.press/v267/talpini25a.html}, abstract = {One-Shot Federated Learning (FL) is a recent paradigm that enables multiple clients to cooperatively learn a global model in a single round of communication with a central server. In this paper, we analyze the One-Shot FL problem through the lens of Bayesian inference and propose FedBEns, an algorithm that leverages the inherent multimodality of local loss functions to find better global models.Our algorithm leverages a mixture of Laplace approximations for the clients’ local posteriors, which the server then aggregates to infer the global model. We conduct extensive experiments on various datasets, demonstrating that the proposed method outperforms competing baselines that typically rely on unimodal approximations of the local losses.} }
Endnote
%0 Conference Paper %T FedBEns: One-Shot Federated Learning based on Bayesian Ensemble %A Jacopo Talpini %A Marco Savi %A Giovanni Neglia %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-talpini25a %I PMLR %P 58448--58466 %U https://proceedings.mlr.press/v267/talpini25a.html %V 267 %X One-Shot Federated Learning (FL) is a recent paradigm that enables multiple clients to cooperatively learn a global model in a single round of communication with a central server. In this paper, we analyze the One-Shot FL problem through the lens of Bayesian inference and propose FedBEns, an algorithm that leverages the inherent multimodality of local loss functions to find better global models.Our algorithm leverages a mixture of Laplace approximations for the clients’ local posteriors, which the server then aggregates to infer the global model. We conduct extensive experiments on various datasets, demonstrating that the proposed method outperforms competing baselines that typically rely on unimodal approximations of the local losses.
APA
Talpini, J., Savi, M. & Neglia, G.. (2025). FedBEns: One-Shot Federated Learning based on Bayesian Ensemble. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:58448-58466 Available from https://proceedings.mlr.press/v267/talpini25a.html.

Related Material